Re: [PATCH RFC] IPv6: Avoid taking write lock for /proc/net/ipv6_route

From: Josh Hunt
Date: Sat Dec 31 2011 - 14:50:10 EST


On Fri, Dec 30, 2011 at 4:09 PM, David Miller <davem@xxxxxxxxxxxxx> wrote:
> From: Josh Hunt <joshhunt00@xxxxxxxxx>
> Date: Wed, 28 Dec 2011 17:23:07 -0600
>
>> lock_stat shows taking the write lock is causing the slowdown. Using
>> this info I decided to write a version of fib6_clean_all() which
>> replaces write_lock_bh(&table->tb6_lock) with
>> read_lock_bh(&table->tb6_lock). With this new function I see the same
>> results as with my rtnetlink iperf test. I guess my question is what
>> am I missing? Is there a reason you need to take the write lock when
>> reading the route table to display to proc?
>
> You're not missing anything, it's just an oversight or laziness. :-)
>
> I've applied your patch thanks.
>
> Longer term we should make the ipv6 tree traversals RCU safe just
> like net/ipv4/fib_trie.c is.  Then we can do away with even the
> read locks for read-only traversals.
>

Thanks David. Are you aware if anyone has started the work to make
IPv6 traversals RCU safe?
--
Josh
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/